Trustworthy AI in the Agentic Lakehouse: from Concurrency to Governance

• URL: http://arxiv.org/abs/2511.16402v1
• Date: Thu, 20 Nov 2025 14:21:34 GMT
• Title: Trustworthy AI in the Agentic Lakehouse: from Concurrency to Governance
• Authors: Jacopo Tagliabue, Federico Bianchi, Ciro Greco,
• Abstract summary: We argue that the path to trustworthy agentic begins with solving the infrastructure problem first.<n>We propose an agent-first design, Bauplan, that re-implements data and compute isolation in the lakehouse.<n>We conclude by sharing a reference implementation of a self-healing pipeline in Bauplan.
• Score: 5.3013727160110085
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Even as AI capabilities improve, most enterprises do not consider agents trustworthy enough to work on production data. In this paper, we argue that the path to trustworthy agentic workflows begins with solving the infrastructure problem first: traditional lakehouses are not suited for agent access patterns, but if we design one around transactions, governance follows. In particular, we draw an operational analogy to MVCC in databases and show why a direct transplant fails in a decoupled, multi-language setting. We then propose an agent-first design, Bauplan, that reimplements data and compute isolation in the lakehouse. We conclude by sharing a reference implementation of a self-healing pipeline in Bauplan, which seamlessly couples agent reasoning with all the desired guarantees for correctness and trust.

Related papers

• Building a Correct-by-Design Lakehouse. Data Contracts, Versioning, and Transactional Pipelines for Humans and Agents [1.9161188920101901]
  Bauplan is a code-first lakehouse that aims to make (most) illegal states unrepresentable using familiar abstractions.<n>Bauplan acts along three axes: typed table contracts to make pipeline boundaries checkable, Git-like data versioning for review and runtime, and transactional runs that guarantee pipeline-level atomicity.
  arXiv  Detail & Related papers  (2026-02-02T16:58:38Z)
• The Why Behind the Action: Unveiling Internal Drivers via Agentic Attribution [63.61358761489141]
  Large Language Model (LLM)-based agents are widely used in real-world applications such as customer service, web navigation, and software engineering.<n>We propose a novel framework for textbfgeneral agentic attribution, designed to identify the internal factors driving agent actions regardless of the task outcome.<n>We validate our framework across a diverse suite of agentic scenarios, including standard tool use and subtle reliability risks like memory-induced bias.
  arXiv  Detail & Related papers  (2026-01-21T15:22:21Z)
• Towards Verifiably Safe Tool Use for LLM Agents [53.55621104327779]
  Large language model (LLM)-based AI agents extend capabilities by enabling access to tools such as data sources, APIs, search engines, code sandboxes, and even other agents.<n>LLMs may invoke unintended tool interactions and introduce risks, such as leaking sensitive data or overwriting critical records.<n>Current approaches to mitigate these risks, such as model-based safeguards, enhance agents' reliability but cannot guarantee system safety.
  arXiv  Detail & Related papers  (2026-01-12T21:31:38Z)
• Let It Flow: Agentic Crafting on Rock and Roll, Building the ROME Model within an Open Agentic Learning Ecosystem [90.17610617854247]
  We introduce the Agentic Learning Ecosystem (ALE), a foundational infrastructure that optimize the production pipeline for agentic model.<n>ALE consists of three components: ROLL, a post-training framework for weight optimization; ROCK, a sandbox environment manager for trajectory generation; and iFlow CLI, an agent framework for efficient context engineering.<n>We release ROME, an open-source agent grounded by ALE and trained on over one million trajectories.
  arXiv  Detail & Related papers  (2025-12-31T14:03:39Z)
• What's the next frontier for Data-centric AI? Data Savvy Agents [71.76058707995398]
  We argue that data-savvy capabilities should be a top priority in the design of agentic systems.<n>We propose four key capabilities to realize this vision: Proactive data acquisition, Sophisticated data processing, Interactive test data synthesis, and Continual adaptation.
  arXiv  Detail & Related papers  (2025-11-02T17:09:29Z)
• Alita-G: Self-Evolving Generative Agent for Agent Generation [54.49365835457433]
  We present ALITA-G, a framework that transforms a general-purpose agent into a domain expert.<n>In this framework, a generalist agent executes a curated suite of target-domain tasks.<n>It attains strong gains while reducing computation costs.
  arXiv  Detail & Related papers  (2025-10-27T17:59:14Z)
• The Gatekeeper Knows Enough [0.0]
  Gatekeeper Protocol is a domain-agnostic framework that governs agent-system interactions.<n>Our results show that this approach significantly increases agent reliability, improves computational efficiency by minimizing token consumption, and enables scalable interaction with complex systems.
  arXiv  Detail & Related papers  (2025-10-16T17:00:42Z)
• Safe, Untrusted, "Proof-Carrying" AI Agents: toward the agentic lakehouse [3.6729718095918393]
  API-first, programmable lakehouses provide the right abstractions for safe-by-design, agentic lakehouses.<n>We present a proof-of-concept in which agents repair data pipelines using correctness checks inspired by proof-carrying code.
  arXiv  Detail & Related papers  (2025-10-10T17:18:36Z)
• From Cloud-Native to Trust-Native: A Protocol for Verifiable Multi-Agent Systems [7.002091295810318]
  We introduce TrustTrack, a protocol that embeds structural guarantees directly into agent infrastructure.<n>TrustTrack reframes how intelligent agents operate across organizations and jurisdictions.<n>We argue that the Cloud -> AI -> Agent -> Trust transition represents the next architectural layer for autonomous systems.
  arXiv  Detail & Related papers  (2025-07-25T04:38:38Z)
• A Pre-training Framework for Relational Data with Information-theoretic Principles [57.93973948947743]
  We introduce Task Vector Estimation (TVE), a novel pre-training framework that constructs supervisory signals via set-based aggregation over relational graphs.<n>TVE consistently outperforms traditional pre-training baselines.<n>Our findings advocate for pre-training objectives that encode task heterogeneity and temporal structure as design principles for predictive modeling on relational databases.
  arXiv  Detail & Related papers  (2025-07-14T00:17:21Z)
• Agent KB: Leveraging Cross-Domain Experience for Agentic Problem Solving [62.71545696485824]
  We introduce AGENT KB, a universal memory infrastructure enabling seamless experience sharing across heterogeneous agent frameworks without retraining.<n>AGENT KB aggregates trajectories into a structured knowledge base and serves lightweight APIs.<n>We validate AGENT across major frameworks on GAIA, Humanity's Last Exam, GPQA, and SWE-bench.
  arXiv  Detail & Related papers  (2025-07-08T17:59:22Z)
• AgentDAM: Privacy Leakage Evaluation for Autonomous Web Agents [66.29263282311258]
  We introduce a new benchmark AgentDAM that measures if AI web-navigation agents follow the privacy principle of data minimization''<n>Our benchmark simulates realistic web interaction scenarios end-to-end and is adaptable to all existing web navigation agents.
  arXiv  Detail & Related papers  (2025-03-12T19:30:31Z)
• Using Petri Nets as an Integrated Constraint Mechanism for Reinforcement Learning Tasks [3.105112058253643]
  Lack of trust in algorithms is usually an issue when using Reinforcement Learning (RL) agents for control in real-world domains. We propose an approach that uses Petri nets (PNs) with three main advantages over typical RL approaches.
  arXiv  Detail & Related papers  (2024-07-05T13:04:06Z)
• Pangu-Agent: A Fine-Tunable Generalist Agent with Structured Reasoning [50.47568731994238]
  Key method for creating Artificial Intelligence (AI) agents is Reinforcement Learning (RL) This paper presents a general framework model for integrating and learning structured reasoning into AI agents' policies.
  arXiv  Detail & Related papers  (2023-12-22T17:57:57Z)
• A Distributed Trust Framework for Privacy-Preserving Machine Learning [4.282091426377838]
  This paper outlines a distributed infrastructure which is used to facilitate peer-to-peer trust between distributed agents. We detail a proof of concept using Hyperledger Aries, Decentralised Identifiers (DIDs) and Verifiable Credentials (VCs)
  arXiv  Detail & Related papers  (2020-06-03T18:06:13Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.